Silence calculator
To provide a more natural sounding set of voice prompts of an interactive voice response (IVR) script, the voice recordings of the prompts may be modified to have a predetermined amount of silence at the end of the recording. The amount of silence required can be determined from the context in which the voice prompt appears in the IVR script. Different contexts may include mid-sentence, terminating in a comma, or a sentence ending context. These contexts may require silence periods of 100 ms, 250 ms and 500 ms respectively. Voice files may be trimmed to remove any existing silence and then the required silence period may be added.
1. A method for processing a plurality of recordings of a plurality of unique voice prompts of an interactive voice response (IVR) program, the method comprising:
identifying a context of a unique voice prompt of the plurality of unique voice prompts;
identifying a fixed period of silence required for a recording of the unique voice prompt based on the context;
generating a modified recording of the unique voice prompt by:
cropping an initial period of silence from an end of the recording of the unique voice prompt to create a cropped recording, and
adding the fixed period of silence to an end of the cropped; and
storing the modified recording of the unique voice prompt recording.
2. The method of claim 1 , wherein the identifying the context comprises:
identifying a punctuation context at an ending of a text script of the unique voice prompt.
3. The method of claim 2 , wherein the punctuation context comprises at least one of:
a sentence ending punctuation, a comma or a semi-colon, and no punctuation.
4. The method of claim 3 , wherein the period of silence is different for each of the punctuation contexts.
5. The method of claim 1 , wherein the cropping an initial period of silence further comprises:
cropping an initial period of silence from a start of the recording of the unique voice prompt.
6. The method of claim 1 , comprising:
generating a list comprising two or more unique voice prompts of the plurality of unique voice prompts, each of the two or more unique prompts having a filename;
identifying a context of the two or more unique voice prompts;
identifying a period of silence in respective recordings of the two or more unique voice prompts based on their respective contexts;
modifying the filenames of the two or more unique voice prompts to indicate the identified periods of silence for the respective recordings of the two or more unique voice prompts;
grouping the filenames into groups of equal periods of silence; and
generating a modified recording of each of the two or more unique voice prompts by adding a period of silence corresponding to a corresponding group of the two or more unique voice prompts.
7. A system for processing a plurality of recordings of a plurality of unique voice prompts of an interactive voice response (IVR) program, the system comprising a silence processing module comprising at least one processor and at least one operatively associated memory, the silence processing module programmed to:
identify a context of a unique voice prompt of the plurality of unique voice prompts in the IVR program;
identify a fixed period of silence required for a recording of the unique voice prompt based on the context;
generate a modified recording of the unique voice prompt by:
cropping an initial period of silence from an end of the recording of the unique voice prompt to create a cropped recording, and
adding the fixed period of silence to an end of the cropped; and
store the modified recording of the unique voice prompt recording.
8. The system of claim 7 , wherein the context comprises:
a punctuation context at an ending of a text script of the unique voice prompt.
9. The system of claim 8 , wherein the punctuation context comprises at least one of:
a sentence ending punctuation, a comma or a semi-colon, and no punctuation.
10. The system of claim 9 , wherein the period of silence is different for each of the punctuation contexts.
11. The system of claim 7 , wherein, when the silence processing module is programmed to crop an initial period of silence, the silence processing module is further programmed to:
crop an initial period of silence from a start of the recording of the unique voice prompt.
12. The system of claim 7 , wherein the silence processing module is further programmed to:
generate a list comprising two or more unique voice prompts of the plurality of unique voice prompts, each of the two or more unique prompts having a filename;
identify a context of the two or more unique voice prompts;
identify a period of silence in respective recordings of the two or more unique voice prompts based on their respective contexts;
modify the filenames of the two or more unique voice prompts to indicate the identified periods of silence for the respective recordings of the two or more unique voice prompts;
group the filenames into groups of equal periods of silence; and
generate a modified recording of each of the two or more unique voice prompts by adding a period of silence corresponding to a corresponding group of the two or more unique voice prompts.
13. A non-transitory computer readable medium comprising instructions that when executed by a processor cause the processor to perform:
identifying a context of a unique voice prompt of the plurality of unique voice prompts;
identifying a fixed period of silence required for a recording of the unique voice prompt based on the context;
generating a modified recording of the unique voice prompt by:
cropping an initial period of silence from an end of the recording of the unique voice prompt to create a cropped recording, and
adding the fixed period of silence to an end of the cropped; and
storing the modified recording of the unique voice prompt recording.
14. The non-transitory computer readable medium of claim 13 , wherein the instructions further cause the processor to perform:
identifying a punctuation context at an ending of a text script of the unique voice prompt.
15. The non-transitory computer readable medium of claim 14 , wherein the punctuation context comprises at least one of:
a sentence ending punctuation, a comma or a semi-colon, and no punctuation.
16. The non-transitory computer readable medium of claim 15 , wherein the period of silence is different for each of the punctuation contexts.
17. The non-transitory computer readable medium of claim 13 , wherein the cropping an initial period of silence further comprises:
cropping an initial period of silence from a start of the recording of the unique voice prompt.